Aaradhya Gupta supervised by Dr. Parameswari Krishnamurthy received his Master of Science – Dual Degree in Computational Linguistics (CLD). Here’s a summary of his research work on Simplifying Medical Language: Lay Summarization of Biomedical Literature using Modular, Domain Aware AI Pipelines:
The growing availability of biomedical research has increased demand for accessible scientific communication, especially for patients, caregivers, and non-expert readers. However, medical texts—such as journal abstracts and clinical content—often contain dense information and specialized terminology, hindering comprehension. This thesis presents a modular AI pipeline designed for lay language summarization, transforming complex biomedical paragraphs into simplified, layperson-friendly versions while preserving factual correctness and essential content.
The system comprises:
- A BioBERT-based term identification module for detecting biomedical jargon.
- A UMLS-backed definition retriever that supplies lay-level definitions.
- A large language model (LLM) that reconstructs and iteratively simplifies content.
The pipeline was evaluated on biomedical texts from PLOS and eLife journals. Performance was assessed using:
- Relevance & Content Preservation: ROUGE, BLEU, METEOR, BERTScore
- Readability: FKGL, DCRS, CLI, LENS 1
- Factual Consistency: AlignScore, SummaC
Human evaluations and ablation studies confirmed the system’s effectiveness in improving lay comprehension. Notably, the pipeline ranked 1st in the BioLaySumm 2025 shared task under the external knowledge subtask, demonstrating state-of-the-art performance in readability and factuality.
November 2025